Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4530 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2695. Min Range: -0.2695

Max Act: 0.2695. Min Act: -0.0000

Data Index: 240156 (C4 (Web Text))

Max Activating Token Index: 504

Text #1

Max Range: 0.2695. Min Range: -0.2695

Max Act: 0.2574. Min Act: -0.0000

Data Index: 272822 (C4 (Web Text))

Max Activating Token Index: 202

Text #2

Max Range: 0.2695. Min Range: -0.2695

Max Act: 0.2649. Min Act: -0.0000

Data Index: 217649 (C4 (Web Text))

Max Activating Token Index: 356

Text #3

Max Range: 0.2695. Min Range: -0.2695

Max Act: 0.2439. Min Act: -0.0000

Data Index: 1146684 (C4 (Web Text))

Max Activating Token Index: 288

Text #4

Max Range: 0.2695. Min Range: -0.2695

Max Act: 0.2057. Min Act: -0.0000

Data Index: 1075477 (C4 (Web Text))

Max Activating Token Index: 134

Text #5

Max Range: 0.2695. Min Range: -0.2695

Max Act: 0.2181. Min Act: -0.0000

Data Index: 265940 (C4 (Web Text))

Max Activating Token Index: 449

Text #6

Max Range: 0.2695. Min Range: -0.2695

Max Act: 0.1848. Min Act: -0.0000

Data Index: 1006375 (C4 (Web Text))

Max Activating Token Index: 132

Text #7

Max Range: 0.2695. Min Range: -0.2695

Max Act: 0.1837. Min Act: -0.0000

Data Index: 1172025 (C4 (Web Text))

Max Activating Token Index: 374

Text #8

Max Range: 0.2695. Min Range: -0.2695

Max Act: 0.1770. Min Act: -0.0000

Data Index: 941946 (C4 (Web Text))

Max Activating Token Index: 276

Text #9

Max Range: 0.2695. Min Range: -0.2695

Max Act: 0.1621. Min Act: -0.0000

Data Index: 533687 (C4 (Web Text))

Max Activating Token Index: 830

Text #10

Max Range: 0.2695. Min Range: -0.2695

Max Act: 0.1742. Min Act: -0.0000

Data Index: 1191747 (C4 (Web Text))

Max Activating Token Index: 936

Text #11

Max Range: 0.2695. Min Range: -0.2695

Max Act: 0.1501. Min Act: -0.0000

Data Index: 1109001 (C4 (Web Text))

Max Activating Token Index: 1008

Text #12

Max Range: 0.2695. Min Range: -0.2695

Max Act: 0.1661. Min Act: -0.0000

Data Index: 1196208 (C4 (Web Text))

Max Activating Token Index: 665

Text #13

Max Range: 0.2695. Min Range: -0.2695

Max Act: 0.1523. Min Act: -0.0000

Data Index: 1290172 (C4 (Web Text))

Max Activating Token Index: 193

Text #14

Max Range: 0.2695. Min Range: -0.2695

Max Act: 0.1625. Min Act: -0.0000

Data Index: 1148744 (C4 (Web Text))

Max Activating Token Index: 57

Text #15

Max Range: 0.2695. Min Range: -0.2695

Max Act: 0.1486. Min Act: -0.0000

Data Index: 281515 (C4 (Web Text))

Max Activating Token Index: 126

Text #16

Max Range: 0.2695. Min Range: -0.2695

Max Act: 0.1427. Min Act: -0.0000

Data Index: 953027 (C4 (Web Text))

Max Activating Token Index: 740

Text #17

Max Range: 0.2695. Min Range: -0.2695

Max Act: 0.1592. Min Act: -0.0000

Data Index: 887309 (C4 (Web Text))

Max Activating Token Index: 690

Text #18

Max Range: 0.2695. Min Range: -0.2695

Max Act: 0.1596. Min Act: -0.0000

Data Index: 858359 (C4 (Web Text))

Max Activating Token Index: 748

Text #19

Max Range: 0.2695. Min Range: -0.2695

Max Act: 0.1521. Min Act: -0.0000

Data Index: 696987 (C4 (Web Text))

Max Activating Token Index: 128